© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92802
    Prev
    Next
    INDEX
    Explanations

    Acronyms and abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ign
    -0.73
    ppus
    -0.65
     canvas
    -0.64
    VIAF
    -0.63
    rostis
    -0.63
     оригіналу
    -0.62
     constitutions
    -0.62
    oor
    -0.62
     Canvas
    -0.60
    Демографія
    -0.60
    POSITIVE LOGITS
     diting
    0.47
    RefNanny
    0.46
     discontinue
    0.43
    aroon
    0.42
     hjælp
    0.41
    väll
    0.41
     hilt
    0.41
    IndentedString
    0.41
     risorse
    0.40
     gouttes
    0.40
    Activations Density 0.100%

    No Known Activations